Papers and Programs


This section includes papers that are being worked on, programs that I find useful, and data sets that I have published about, for re-analysis. The programs are all written for DOS, but so far they work in Windows. They are written in Turbo Pascal, source code is available if you want that. The papers et cetera are in Adobe PDF format. The data files are compressed ZIP files. You need an unzip utility to decompress those. Personally, I like WinZip, but other programs are also fine. There are also a few draft chapters of my book 'Multilevel Analysis. Techniques and Applications'. As always, I welcome comments and corrections!

A paper describing .web coverage bias in Europe across time and countries is Mohorko, A., de Leeuw, E., and Hox, J. (2011). Internet coverage and coverage bias in countries across Europe and over time: Background, methods, question wording and bias tables.


An upcoming new chapter on multilevel analysis of ordinal and count data.


An upcoming new chapter on multilevel CFA.


Here is a copy of an SPSS Mixed introduction that walks you through SPSS Mixed using examples from my multilevel book. The data files from this book are also on this homepage.


  Here are the transparancies of the presentation on Sample Size and Robustness Issues in the Complex Data session at the I.S.A. International Conference in Brisbane, july 7-13, 2002.

Below are copies of papers (co)authored at the Fifth International Conference on Logic and Methodology in Cologne, 2000. According to the publication manual of the American Psychological Association, this CD-ROM should be referred to as in the following example: Author, I. (2002). Title of paper [CD-Rom]. In: J. Blasius, J. Hox, E. de Leeuw & P. Schmidt (Eds.), Social science methodology in the new millennium. Opladen, FRG: Leske + Budrich. This means that it is referred to as a normal edited volume, but the medium (CD-Rom) is added to the title and there are no page numbers. If want to order dis CD-Rom, go to Leske+Budrich.

G.J.L.M. Lensvelt-Mulders & J.J. Hox. How to measure sensitive topics: A meta-analysis.

N. Borgers & J.J. Hox. Reliability of responses in self-administered questionnaires: Researech with children.

E. de Leeuw, J. Hox, S. Kef & M. van Hattum. Overcoming the problems of special interviews on sensitive topics: Computer assisted self-interviewing tailored for special populations.

C.J.M. Maas & J.J. Hox. Robustness of multilevel parameter estimates.

J.J. Hox. Multilevel multivariate and structural equation models: Some missing links.


Alfatest: a program to test the difference between two or more reliability coefficients alpha.

Split2: a program to compute the pooled-within and scaled-between covariance matrices needed for multilevel covariance structure analysis using Muthén's approximate solution.

Probs: a simple program to compute p-values for Z, t, chi*2, and F. If you are serious about probability values, get the free NCSS statistical calculator at the NCSS download page.

Aberrant: a program to compute a number of indices of aberrant response behavior on scales. Described in a paper in Bulletin de Méthodologie Sociologique (in English) that is in the publications section.

Kappa: a program originally written by Luuk Wouters to calculate Cohen's Kappa coefficient of agreement for nominal scales.


  Transparencies of the presentation for 'Uw Mening Telt' on June 5, 2000, on two international comparison studies on household survey nonresponse.

  Transparencies of the presentation about multilevel longitudinal modeling at the International Seminar organized by the Research Institute of Psychology and Health, in Utrecht on April, 27-28, 2000. These are imported WordPervert documents, which may have a disturbed lay-out.

   Transparencies of the presentation about analyzing interventions in organizations at the International Seminar organized by the Research Institute of Psychology and Health, in Utrecht on November 7-8, 2002.

This is the draft chapter of my multilevel book on latent growth curve models

Some more details on multilevel regression models for longitudinal data are in the draft version of the chapter on this topic.

And here is the draft version version of the chapter on multilevel modeling of dichotomous data and proportions.

  The data from the examples in the book chapter 'Multilevel analysis of grouped and longitudinal data.' These were also used in the presentation presentation about multilevel longitudinal modeling at the International Seminar organized by the Research Institute of Psychology and Health, in Utrecht on April, 27-28, 2000.

   Transparencies of the presentation about the Bayesian (Markov Chain Monte Carlo) multilevel methods in the program MLwiN, at the September 2000 meeting of the Dutch Multilevel Group. 

Last updated: April, 2003

E-mail to

Back to Joop's homepage